Event Dime

Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs

Festivals & Fairs
When:
June 5, 2026 · 10:43 PM
Where:
A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong
Source:
A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong

This is a small study that explores using tool calls to wrap untrusted parts of prompts. OpenAI's model spec considers tool results the least trusted kind of input. If tool-wrapping helped, it would be an easy way to improve robustness while using existing APIs models already support. In 3 tested tasks it didn't seem to broadly help, and in some cases made things worse. We advocate for more understanding of the instruction hierarchy and ideas around better primitives for untrusted inputs. There

Why this event appears here

This listing is shown because it is tied to the current city coverage and carries structured metadata that can be indexed and compared with other events.

  • City coverage

    A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong

  • Primary source

    A review of Where Is My Flying Car? by J. Storrs Hall — LessWrong

  • Categories

    Festivals & Fairs